Saved in:
Bibliographic Details
Main Authors: Da Silva, Itallo Patrick Castro Alves, Pereira, Emanuel Adler Medeiros, Barboza, Erick de Andrade, Neto, Baldoino Fonseca dos Santos, Ribeiro, Marcio de Medeiros
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.24971
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917178376192000
author Da Silva, Itallo Patrick Castro Alves
Pereira, Emanuel Adler Medeiros
Barboza, Erick de Andrade
Neto, Baldoino Fonseca dos Santos
Ribeiro, Marcio de Medeiros
author_facet Da Silva, Itallo Patrick Castro Alves
Pereira, Emanuel Adler Medeiros
Barboza, Erick de Andrade
Neto, Baldoino Fonseca dos Santos
Ribeiro, Marcio de Medeiros
contents Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider robustness evaluation while validating computer vision systems. This paper presents a comprehensive evaluation of compression techniques - quantization, pruning, and weight clustering applied individually and in combination to convolutional neural networks (ResNet-50, VGG-19, and MobileNetV2). Using the CIFAR-10-C and CIFAR 100-C datasets, we analyze the trade-offs between robustness, accuracy, and compression ratio. Our results show that certain compression strategies not only preserve but can also improve robustness, particularly on networks with more complex architectures. Utilizing multiobjective assessment, we determine the best configurations, showing that customized technique combinations produce beneficial multi-objective results. This study provides insights into selecting compression methods for robust and efficient deployment of models in corrupted real-world environments.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24971
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
Da Silva, Itallo Patrick Castro Alves
Pereira, Emanuel Adler Medeiros
Barboza, Erick de Andrade
Neto, Baldoino Fonseca dos Santos
Ribeiro, Marcio de Medeiros
Computer Vision and Pattern Recognition
Artificial Intelligence
Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider robustness evaluation while validating computer vision systems. This paper presents a comprehensive evaluation of compression techniques - quantization, pruning, and weight clustering applied individually and in combination to convolutional neural networks (ResNet-50, VGG-19, and MobileNetV2). Using the CIFAR-10-C and CIFAR 100-C datasets, we analyze the trade-offs between robustness, accuracy, and compression ratio. Our results show that certain compression strategies not only preserve but can also improve robustness, particularly on networks with more complex architectures. Utilizing multiobjective assessment, we determine the best configurations, showing that customized technique combinations produce beneficial multi-objective results. This study provides insights into selecting compression methods for robust and efficient deployment of models in corrupted real-world environments.
title Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.24971